# Kinaema: a recurrent sequence model for memory and pose in motion

arXiv: https://arxiv.org/abs/2510.20261 · HTML: https://mlsanity.com/paper/2510.20261/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 58 of its 72 references that are in the map.
- First posted on arXiv 23 Oct 2025.

## Builds on (most cited first, 30 of 58)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019)
- [ORB-SLAM: a Versatile and Accurate Monocular SLAM System](https://mlsanity.com/paper/1502.00956/) (2015)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [Vision Transformers Need Registers](https://mlsanity.com/paper/2309.16588/) (2023)
- [AI2-THOR: An Interactive 3D Environment for Visual AI](https://mlsanity.com/paper/1712.05474/) (2017)
- [Neural Turing Machines](https://mlsanity.com/paper/1410.5401/) (2014)
- [Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI](https://mlsanity.com/paper/2109.08238/) (2021)
- [On Evaluation of Embodied Navigation Agents](https://mlsanity.com/paper/1807.06757/) (2018)
- [Gibson Env: Real-World Perception for Embodied Agents](https://mlsanity.com/paper/1808.10654/) (2018)
- [Resurrecting Recurrent Neural Networks for Long Sequences](https://mlsanity.com/paper/2303.06349/) (2023)
- [Reinforcement Learning with Unsupervised Auxiliary Tasks](https://mlsanity.com/paper/1611.05397/) (2016)
- [Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning](https://mlsanity.com/paper/1609.05143/) (2016)
- [xLSTM: Extended Long Short-Term Memory](https://mlsanity.com/paper/2405.04517/) (2024)
- [Learning to Explore using Active Neural SLAM](https://mlsanity.com/paper/2004.05155/) (2020)
- [An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution](https://mlsanity.com/paper/1807.03247/) (2018)
- [DSAC - Differentiable RANSAC for Camera Localization](https://mlsanity.com/paper/1611.05705/) (2016)
- [ViNT: A Foundation Model for Visual Navigation](https://mlsanity.com/paper/2306.14846/) (2023)
- [Learning to Navigate in Complex Environments](https://mlsanity.com/paper/1611.03673/) (2016)
- [CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow](https://mlsanity.com/paper/2211.10408/) (2022)
- [Goal-conditioned Imitation Learning](https://mlsanity.com/paper/1906.05838/) (2019)
- [CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion](https://mlsanity.com/paper/2210.10716/) (2022)

## Built on by (most cited first, 2 of 2)

- [KV-Tracker: Real-Time Pose Tracking with Transformers](https://mlsanity.com/paper/2512.22581/) (2025)
- [Compressing History into Memory: Distilling Transformers into Recurrent Transformers](https://mlsanity.com/paper/2606.21562/) (2026)

## Abstract (arXiv)

One key aspect of spatially aware robots is the ability to "find their bearings", ie. to correctly situate themselves in previously seen spaces. In this work, we focus on this particular scenario of continuous robotics operations, where information observed before an actual episode start is exploited to optimize efficiency. We introduce a new model, Kinaema, and agent, capable of integrating a stream of visual observations while moving in a potentially large scene, and upon request, processing a query image and predicting the relative position of the shown space with respect to its current position. Our model does not explicitly store an observation history, therefore does not have hard constraints on context length. It maintains an implicit latent memory, which is updated by a transformer in a recurrent way, compressing the history of sensor readings into a compact representation. We evaluate the impact of this model in a new downstream task we call "Mem-Nav". We show that our large-capacity recurrent model maintains a useful representation of the scene, navigates to goals observed before the actual episode start, and is computationally efficient, in particular compared to classical transformers with attention over an observation history.